Solving the big data challenge of medical scientific literature

  • Tanja Novaković ZEM Solutions Ltd.; The Pharmacoeconomics Sections of the Pharmaceutical Association of Serbia
  • Mark Parker ZEM Solutions Ltd.

Abstract


Recent advancements in technology have resulted in an explosion of available evidence collected in real world settings. Automated data collection, along with the digitisation of both medical literature and patient records have changed the face of medical science over the last 10 years. Through the analytics of big data, we can uncover hidden patterns, unknown correlations, trends, preferences, and other information that can help stakeholders make better and more informed decisions. The digitisation of scientific medical literature has given researches unprecedented access to a wealth of medical knowledge. Consequently medical scientific literature is now a big data problem. Current big data analysis techniques are not enough to solve the challenge of analysing large volumes of scientific medical literature. Machine learning and artificial intelligence (AI) provide a toolbox of techniques that can be applied to convert big data into information so it can be applied as knowledge. Through AI, we have an opportunity to do better to address major public health issues, improve health outcomes, reduce costs, ensure patient safety, address equity and equality issues by ensuring all healthcare stakeholders have access to timely, relevant, accurate and evidenced information across the entire decision-making spectrum.

References

Kruse CS, Goswamy R, Raval Y, Marawi S. Challenges and Opportunities of Big Data in Health Care: A Systematic Review. JMIR Med Inform. 2016 Nov 21;4(4):e38.

Drummond M, Sculpher M, Claxton K, Stoddart G, George, Torrance G. Methods for the Economic Evaluation of Health Care Programmes. Oxford University Press, 2015

Published
2022/10/18
Section
Invited lectures Session 2